Analysis Of Prediction For The Stage And Thickness For Ice Jam Based On Artificial Intelligence Methods

Prediction of the stage and thickness for ice jam is great significance not only to research the principle of ice jam development, but also provide reference for the dike construction of hydraulic structures and ice-jam flood control. When analysis the field data from Hequ region to the Yellow River. We used four methods building the model of stage and thickness for ice jam in the Hequ region to the Yellow River. They are support vector machines, the traditional BP artificial neural network, genetic algorithms optimize neural network and multiple regression analysis. Forecasts include this section and section between the upper and lower. While in the control of experimental conditions, we also analysis the measured data from thirteen sections of Ice jam test and seven observation sections of Backwater Test by the same four methods were used to set up stage and thickness for ice jam Prediction model, predictive value will be obtained and measured values within the scope of the information contrast, but also on the four methods for the prediction of contrast, the results can be seen by comparison, both in natural rivers or in the laboratory under controlled conditions, The artificial intelligence methods which support vector machines, BP artificial neural network, Genetic Algorithm optimization neural network have more advantage than multiple regression analysis both in the prediction accuracy and complex environmental adaptability, genetic algorithm optimization neural network model is particularly evident advantages, for the frozen rivers of ice forecasting model established to provide useful and important help reference.